code-review-helper
Proporciona ayuda para revisar código siguiendo las mejores prácticas de Roastr, verificando calidad, seguridad y documentación antes de crear un PR.
Proporciona ayuda para revisar código siguiendo las mejores prácticas de Roastr, verificando calidad, seguridad y documentación antes de crear un PR.
Strict validator. Runs format, lint, types, and build checks via script.
Resolve ambiguities and markers in validation.yaml interactively. Updates spec docs directly with full audit trail.
Generates sonar-project.properties for SonarQube code quality analysis and coverage reporting. Auto-detects test framework (Jest/Vitest) and configures coverage paths.
Generates .prettierignore to exclude build outputs, dependencies, and generated files from Prettier formatting. Prevents formatting of dist/, node_modules/, and coverage/ directories.
Apply when writing styles. Ensures consistency with design system and project patterns.
Python development best practices, patterns, and conventions. Use when writing Python code, reviewing .py files, discussing pytest, asyncio, type hints, pydantic, dataclasses, or Python project structure. Triggers on mentions of Python, pytest, mypy, ruff, black, FastAPI, Django, Flask.
WHEN: General Python code review, PEP8 compliance, type hints, Pythonic patterns WHAT: PEP8/style check + Type hint validation + Pythonic idioms + Error handling + Documentation WHEN NOT: FastAPI → fastapi-reviewer, Django → django-reviewer, Data science → python-data-reviewer
Python best practices and patterns. Use when writing, reviewing, or debugging Python code. Provides PEP 8 guidance, type hints, testing with pytest, and async patterns.
TRUST quality principles (Test-first, Readable, Unified, Secured, Trackable) ensuring production-ready code. Use when implementing, reviewing, testing, or evaluating code quality across all development phases.
Perform a code review focused on bugs, risks, regressions, and missing tests.
Fixes error handling issues including floating promises, silent catches, and throwing non-Error objects. Use when encountering @typescript-eslint/no-floating-promises, silent catch blocks, or throw statement issues.
C++23 best practices with Google Test 1.15, clang-format 19, and modern C++ standards.
Run automatically after completing any code changes. Validates TypeScript build, auto-fixes prettier and linting, then manually fixes any remaining issues.
Validate builds, type checks, and linting after code changes. Use proactively before finishing tasks or opening PRs.
Comprehensive code review methodology. 4 layers (Correctness, Security, Performance, Style), severity classification, 80% confidence threshold.
Use proactively to ensure code quality through reviews and testing. This is particularly important after code generation or changes.
WHEN: Deep AI-powered code analysis, multi-model code review, security scanning with Codex and Gemini WHAT: Comprehensive code review using external AI models with severity-based findings, deduplication, and secret detection WHEN NOT: Simple lint checks -> code-reviewer, Quick security only -> security-scanner, Style formatting -> code-quality-checker
Review configuration, secrets, and environment handling. Checks for safe defaults, secret management, feature flags, and environment parity. Use when reviewing config files, environment variables, or feature flags.
Analyze type design quality and invariants. Use when introducing new types, during PR creation with data models, or when refactoring type designs.
Comprehensively reviews Python libraries for quality across project structure, packaging, code quality, testing, security, documentation, API design, and CI/CD. Provides actionable feedback and improvement recommendations. Use when evaluating library health, preparing for major releases, or auditing dependencies.
変更されたコードの品質をレビューし、問題点や改善提案を報告します。PR作成前のセルフレビュー、コーディング規約のチェック、セキュリティリスクの検出に使用してください。
Use when writing or reviewing TypeScript code, or when the user mentions TypeScript, strict typing, type errors, or type safety.